Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    purpose or goal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    每个
    0.43
     στην
    0.41
    指向
    0.41
    อยู่ใน
    0.40
    我们在
    0.39
    ្នុង
    0.38
     Within
    0.38
     στον
    0.37
     ใน
    0.37
     Vers
    0.36
    POSITIVE LOGITS
     sostegno
    0.47
     inspect
    0.44
     supporto
    0.44
    寻求
    0.42
     inquire
    0.42
     확인
    0.41
     exchange
    0.41
     renegoti
    0.41
    exchange
    0.40
     recoger
    0.40
    Act Density 0.096%

    No Known Activations